相关疑难解决方法(0)

我有两个网络:一个Model生成输出,一个Adversary对输出进行分级.

两者都经过单独培训,但现在我需要在单个会话期间将它们的输出结合起来.

我试图实现这篇文章中提出的解决方案:同时运行多个预先训练的Tensorflow网络

我的代码

with tf.name_scope("model"):
    model = Model(args)
with tf.name_scope("adv"):
    adversary = Adversary(adv_args)

#...

with tf.Session() as sess:
    tf.global_variables_initializer().run()

    # Get the variables specific to the `Model`
    # Also strip out the surperfluous ":0" for some reason not saved in the checkpoint
    model_varlist = {v.name.lstrip("model/")[:-2]: v 
                     for v in tf.global_variables() if v.name[:5] == "model"}
    model_saver = tf.train.Saver(var_list=model_varlist)
    model_ckpt = tf.train.get_checkpoint_state(args.save_dir)
    model_saver.restore(sess, model_ckpt.model_checkpoint_path)

    # Get the variables specific to the `Adversary`
    adv_varlist = {v.name.lstrip("avd/")[:-2]: v …

我有一个基于TensorFlow的神经网络和一组变量.

培训功能如下:

def train(load = True, step)
    """
    Defining the neural network is skipped here
    """

    train_step = tf.train.AdamOptimizer(1e-4).minimize(mse)
    # Saver
    saver = tf.train.Saver()

    if not load:
        # Initalizing variables
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, 'Variables/map.ckpt')
        print 'Model Restored!'

    # Perform stochastic gradient descent
    for i in xrange(step):
        train_step.run(feed_dict = {x: train, y_: label})

    # Save model
    save_path = saver.save(sess, 'Variables/map.ckpt')
    print 'Model saved in file: ', save_path
    print 'Training Done!'

我正在调用这样的训练函数:

# First train
train(False, 1)
# Following train
for i …